physics-benchmark

Tag

Cards List
#physics-benchmark

Hierarchical Experimentalist Agents

Hugging Face Daily Papers · 2026-06-28 Cached

Introduces HExA, a training-free framework enabling LLMs to learn through active experimentation and skill reuse, achieving up to 77% success on the new Interphyre physics benchmark, a large improvement over existing agents.

0 favorites 0 likes
← Back to home

Submit Feedback